Icon

KT_​PP-G1

02_LSTM_Network

This workflow predicts time series (energy consumption) by an LSTM network with lagged values as input. The trained model is then used for out-of-sample forecasting. The forecasted values are compared to the actual values, and the performance of the forecast is reported via scoring metrics and a line plot.

URL: "Once Upon A Time..." by LSTM Network https://www.knime.com/blog/text-generation-with-lstm

Network Architecture Data Loading Data Cleaning Create Input Vector convertdate/timeinto Date&Time objects80/20 splitcombine intolistlag 200 valuestraining withMSE loss functionNode 513 Missing Value String to Date&Time Column Filter Timestamp Alignment Partitioning Column Aggregator Lag Column Keras Input Layer Keras SimpleRNN Layer Keras Dense Layer Keras NetworkLearner Deployment Loop Line Plot(JavaScript) Numeric Scorer CSV Reader Network Architecture Data Loading Data Cleaning Create Input Vector convertdate/timeinto Date&Time objects80/20 splitcombine intolistlag 200 valuestraining withMSE loss functionNode 513 Missing Value String to Date&Time Column Filter Timestamp Alignment Partitioning Column Aggregator Lag Column Keras Input Layer Keras SimpleRNN Layer Keras Dense Layer Keras NetworkLearner Deployment Loop Line Plot(JavaScript) Numeric Scorer CSV Reader

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
On NodePit since: 2025-01-13
Last update: 2025-02-04
Created with KNIME version: v5.4.0
Tags: Time SeriesPredictionEnergy UsageLSTMDeep LearningNeural NetworkKeras

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!